JP2007531141A - Driving multiple applications with a common dialog management system - Google Patents

Abstract

The invention describes a method for driving multiple applications (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>) by a common dialog management system ( 1 ). Therein, a unique set of auditory icons (S<SUB>1</SUB>, S<SUB>2</SUB>, S<SUB>3</SUB>, . . . , S<SUB>n</SUB>) is assigned to each application (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>). The common dialog management system ( 1 ) informs a user of the status of an application (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>) by playback, at a specific point in a dialog flow, of a relevant auditory icon (I<SUB>1</SUB>, I<SUB>2</SUB>, I<SUB>3</SUB>, . . . , I<SUB>n</SUB>) selected from the unique set of auditory icons (S<SUB>1</SUB>, S<SUB>2</SUB>, S<SUB>3</SUB>, . . . , S<SUB>n</SUB>) of the respective application (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>) Moreover the invention describes a dialog management system comprising an input detection arrangement ( 4 ) for detecting user input ( 5 ) to the system, a sound output arrangement ( 6 ) for outputting audible sound ( 7 ), a core dialog engine ( 8 ) for coordinating a dialog flow by interpreting user input ( 5 ) and synthesizing audible sound output ( 7 ), an application interface ( 10 ) for communication between the dialog management system ( 1 ) and the applications (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>), a source of unique sets of auditory icons (S<SUB>1</SUB>, S<SUB>2</SUB>, S<SUB>3</SUB>, . . . , S<SUB>n</SUB>) assigned to the applications (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>), and an auditory icon management unit ( 11 ) for selecting relevant auditory icons (I<SUB>1</SUB>,I<SUB>2</SUB>,I<SUB>3</SUB>, . . . , I<SUB>n</SUB>) corresponding to the applications (A<SUB>1</SUB>, A<SUB>2</SUB>, A<SUB>3</SUB>, . . . , A<SUB>n</SUB>) for playback at specific points in the dialog flow.

Description

Detailed Description of the Invention

  The present invention relates to a method for driving multiple applications with a common at least partially voice-based dialog management system and to a dialog management system for driving multiple applications.

  Recent developments in the field of man-machine interface have led to widespread use of technical devices and applications that are managed or driven by interaction between the application and its users. Most dialog management systems are based on visual information display and manual user interaction. For example, a user can enter a dialog or dialog flow using a personal digital assistant (PDA) to schedule and read incoming mail. The dialog is executed by the dialog management system that issues the prompt, and the user responds to the prompt by pen input or keyboard input. Users can request such an application to report events that are happening now or in the near future. For example, a personal digital assistant can remind the user of appointments and important dates. Reminders may be displayed as graphics on the display, attracting the user's attention with an audible reminder that is an artificial sound such as a beep or ping sound, You may be reminded to see and see messages and reminders from the application. The same type of beep and ping sounds may be used as a general attention-getting device, or different types of sounds may be used to indicate different types of events. Such a beep sound is a word play, but is generally called “earcon”. It means an icon by sound.

  As long as such an interaction is performed between the user and only one application, it is not so difficult to remember which earphones or beeps are used for which event. However, it is very confusing when the dialog management system manages the dialog between the user and multiple applications. This is because the sounds used to indicate various types of events are generally limited to artificially audible electronic noise such as beeps. The user may get confused and mix the sound types and misinterpret the dialog flow.

  However, in an interaction management system that is at least partially voice-based, a user can have a one-way or two-way interaction using an application. The user issues an utterance command and receives visible or audible feedback from the dialog system. One such example is a home electronics management system where a user issues spoken commands and activates a device such as a video recorder. Another example is a car navigation device or other operation, in which a user asks or orders the device and the device answers or asks. More advanced dialog management systems can interpret spoken user inputs by issuing spoken prompts. For example, when a user wants to check the status of his electronic mailbox, he says, "Check my mailbox". The dialog management system sends necessary commands to the application, interprets the results, and then responds as appropriate, such as “mail has arrived” or “mailbox is empty”. However, such spoken feedback may be desired even if it is limited to a simple phrase. This is especially true when the dialog management system is driving multiple applications simultaneously. For example, when the dialog management system controls a personal digital assistant, personal computer, telephone, home entertainment system, news and weather forecast service, the user may be confused by voice feedback. For example, “There was a call from everyone”, “The weather is clear today”, “The Bayern Munich vs. Real Madrid game starts on channel XYZ in 5 minutes. Do you want to record?”, “Within 2 weeks "Do you want to make a reservation?" Or "Internet connection will expire in 5 minutes." Eventually, the user is distracted because many messages are output, even if the messages are meaningful and the information is specifically requested.

  In addition to audio feedback, there is an attempt to provide a dialogue management system that informs the user of the application status via sound icons, “Contextual Awareness, Messaging and Communication in Nomadic Audio Environments” (Nitin Sawnhey, M. SC. Thesis , Massachusetts Institute of Technology, 1998). This document describes a portable device that can interface with a remote server. The status of one or more programs launched on the server can be reported by a portable audio device (typically worn on the user's collar). This device only receives messages from a program running on a remote server and only monitors the operation of the program (all with similar properties) so that it can be viewed as a single application Is. This document does not suggest that a number of individual applications can be operated by a common interactive system, even if they are different in nature, so that the user not only monitors but controls these different applications.

  SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a method that is easy and inexpensive and that allows different applications with which a user interacts to be comfortably and complexly and reliably distinguished using a common dialog management system. In particular, the user should not accidentally issue a command for one application to another application.

  Thus, the present invention provides a method for running multiple applications with a common dialog management system. In the method, a set of unique acoustic icons is assigned to each application, and the common dialog management system selects a related acoustic icon selected from the set of unique acoustic icons of the application at a point in time in the dialog flow. The user is notified of the state of the application by playing it back so that it can be heard. An “acoustic icon” is a type of audio or a dedicated audio chunk that is used to describe a specific type of feedback from an application, for example an artificial short audio chunk (an earphone) or a real world An audio chunk that resembles a sound (for example, a recording of a sound of love).

  The dialog management system according to the present invention comprises the following elements: an input detection mechanism for detecting user input to the system, a voice output mechanism for outputting an audible prompt, and by interpreting the user input and generating an output prompt. The core interaction engine that coordinates the interaction flow, the application interface that communicates between the interaction management system and the application, the source of the set of unique acoustic icons assigned to the application, and plays at the appropriate time during the interaction flow A sound icon management unit that selects a related sound icon from a set of unique sound icons corresponding to the application.

  By operating multiple applications with the dialog management system according to the present invention, the user can easily distinguish between different types of feedback from different applications. Each type of feedback notified by the application is accompanied by a unique and meaningful acoustic sound, so that the user can easily associate it with the corresponding application, and the user is confused by one type of feedback to the other type There is no risk of mistakes. A unique acoustic icon allows the user to be always informed about the currently interacting application. This prevents a user from mistakenly issuing one application as another application and issuing a command. Therefore, the present invention is particularly advantageous in the case of a dialog management system with full voice control. Or, it is particularly advantageous in applications where it is impractical and dangerous that the user has to look at the screen to interact. For example, when the user should not be distracted from traffic conditions, such as in an automobile navigation system, or when the surgeon must be constantly informed about the status of the operation and keep focused on the operation. Therefore, according to the present invention, a large number of individual applications, even of different nature, are driven by a common interactive system and monitored and controlled by the user.

  The dependent claims disclose particularly advantageous embodiments and features of the invention, and the system can be further improved by the features of the method claims.

  The dialog management system according to the present invention can also be incorporated into existing devices such as PCs, televisions, video recorders, etc., and can inform the user of the use of various application states operating in home and / or office environments. . In a preferred embodiment, the dialogue management system is implemented as a stand-alone device and the physical aspect is a robot or preferably a human. The dialogue system may be realized, for example, as a dedicated device described in German Patent Application No. 10249060A1. This device gives the impression that the device is listening to the user's words with the moving part having facial features directed at the user. Such a dialogue management system can also be configured to follow when the user moves from room to room. The interface between the dialog management system and the individual application may be realized by a cable. Preferably, the interface is realized wirelessly (infrared, Bluetooth, etc.), and the dialog management system is basically mobile, and is not limited to the vicinity of the application to be used. If the reach of the wireless interface is long enough, the dialog management system can be used to easily control multiple applications of devices in different rooms (office blocks and private houses) in the building. The interface between the dialog management system and individual applications is preferably managed in a dedicated application interface section. Here, communication between the application and the dialog management system is managed by sending a command or command interpreted from the spoken user input to each application and receiving feedback directed to the user from the application. The application interface unit can process several applications in parallel.

  The application driven by the dialog management system may be a program operating as software on an electronic device controlled by a personal computer, a network, or other processor, or a simple circuit such as a home heating system or a microwave oven. Good. Similarly, an application can be understood as controlling a mechanical or physical device or controlling an object not normally controlled by a processor. Such a device or object may be a purely mechanical device or object, for example a mailbox. An interface between an appropriate sensor and a dialog management system is provided for such an object so that the dialog management system is notified when a mail is put in a mailbox, for example. This event is then notified to the user by an appropriate acoustic icon (eg, post horn sound). In this way, the user of the dialog management system can know that the mail has been delivered without actually going to see it. Such an application of the dialogue management system according to the present invention is particularly advantageous for a user living in a high-rise house or a user with a physical disability. The dialogue management system of the present invention can also control a home-type heating system or the like that can be reprogrammed by the user according to the season. A user can easily reprogram the heating system with an utterance command before going on vacation using the dialog management system. Thus, time-consuming manual reprogramming is not necessary. The dialogue management system can report the status of the heating system to the user, thereby adding an appropriate acoustic icon to the associated prompt. The application may be an essentially electronic device such as an intercom or telephone. Here, the dialogue management system is connected to an intercom or telephone by a suitable interface, so that even if the user does not open the door or pick up the handset, an appropriate sound icon (for example, a visitor at the door) By notifying the user of the event by emitting a sound of knocking the door, the visitor and the phone can be processed to assist the user.

  The user input to the dialogue management system may be a voice, and the user's utterance command or comment can be recorded by an input detection mechanism such as a microphone. The input detection mechanism further includes a keyboard, mouse, and some buttons if the dialog management system is not fully voice controlled, so that the user can enter commands into the system. The advanced input detection mechanism is equipped with a camera that senses the movement of the user, and the user communicates with the dialogue management system through gestures, for example, by shaking hands or shaking the head. The dialog management system interprets the user input, determines the application to which the user input is directed, and converts the user input into a suitable format that the application can understand.

  Analyzes emitted user input and converts feedback from the application into output prompts by the core interaction engine. The dialog management system communicates with the user via a voice output mechanism (preferably one or more loudspeakers) that outputs audible prompts generated by the core dialog engine in response to feedback from the application.

  The core dialog engine has units and modules that perform normal speech recognition and speech synthesis steps. For example, a language understanding unit or a speech synthesis unit. The dialogue control unit interprets the text identified by the language understanding unit, identifies the application to which it is directed, and converts it into a suitable format that can be processed by the application. In addition, the dialog controller analyzes incoming feedback from the application and sends a preferred acoustic icon selected from the set of unique acoustic icons associated with the application to the output audio mechanism. The audible prompt may be thought of as dedicated sound chunks that contain acoustic icons and describe specific types of feedback from the application.

  The application uses an acoustic icon to indicate that an event in the dialog flow or a specific event of interest to the user, such as the arrival of an email, has occurred. Furthermore, an acoustic icon can be used to indicate that the application is waiting for a user response, for example if the user misses a prompt. Acoustic icons can preferably be used to indicate changes in the operating state of the application to be notified to the user.

  The application includes a complete set of acoustic icons that can be used in any situation that allows the application to provide feedback to the user regarding its state or behavior. In a preferred embodiment, the application may provide a copy of the set of sound icons to the dialog management system along with accompanying instructions and accompanying information regarding the preferred use or playback of each sound icon. These icons are managed in the acoustic icon management unit by the dialogue management system. This acoustic icon manager records which acoustic icons are assigned to which applications and the type of feedback each acoustic icon should be used for. The interaction management system may obtain a complete set of acoustic icons at the beginning of the interaction flow between the user and the application, or at the initial launch or incorporation of the application. The acoustic icon management unit may store all information related to the acoustic icon and the instruction accompanying it in the local memory for later use. Thus, the dialog management system has the acoustic icons necessary to provide appropriate feedback to the user whatever happens during the dialog flow.

  Alternatively, the dialogue management system initially provides the application with only relevant identification information (eg, unique descriptive name or number) for each acoustic icon in the set and usage instructions associated with different acoustic icons. You may request. The dialogue management system may then request each required acoustic icon to reduce memory costs. The dialog management system can determine which type of acoustic icon is required for an application in the near future based on the previous interaction flow and request this acoustic icon from the application in advance. Good.

  For applications that do not utilize a predetermined set of acoustic icons, the dialog management system can provide an appropriate set. For this reason, the dialogue management system can determine the nature of the application and can determine a suitable set of acoustic icons. Alternatively, the user can choose to define an acoustic icon himself. The user does this by finding a digital audio chunk by downloading from the Internet or extracting a suitable audio chunk from the soundtrack or song. Alternatively, a voice chunk may be recorded using a recording device, and the recording may be sent to the dialog management system. For example, recording or obtaining a recording of a Formula One racing car and sending the recording to the dialog management system. The acoustic icon manager stores the recording in local memory and instructs the audio chunk to be played whenever an application providing sports news updates the news about Formula One race. The user can also advantageously record a suitable audio chunk using the microphone of the dialog management system. In a preferred embodiment of the present invention, the dialogue management system is a suitable interface connected to a portable memory such as a USB stick, a memory card, or an external network such as the Internet for searching for and downloading audio chunks for use as acoustic icons. With an interface to

  In a particularly preferred embodiment of the invention, the dialog management system can provide the application with the acoustic icons it needs. For example, an application may use only one or two acoustic icons that indicate the start of a process or that indicate that an error has occurred and draw the user's attention. However, in order to intuitively and easily understand the interaction flow between the user and the application, such a small number of options is not sufficient. In this case, the dialog management system can select a suitable set of acoustic icons from the available choices and assign it to the application. In addition, two or more applications may have similar or identical acoustic icons in the repertoire. In order to avoid user confusion when both applications are active at the same time, these acoustic icons can be modified in the dialog management system or replaced by different suitable acoustic icons as well. For example, when loading a new application, the interaction management system looks up the acoustic icon associated with the new application and compares it with the acoustic icons already assigned to other applications. If there are new acoustic icons that are identical or very similar to existing acoustic icons, the dialog management system preferably notifies the user and suggests a suitable alternative acoustic icon if one is available. If there is no suitable sound icon available for replacement, the dialog management system may prompt the user to enter a suitable sound icon.

  Examples of acoustic icons that the application can use to provide audible feedback to the user include a start acoustic icon that plays when the interaction flow between the user and the application is activated or restarted from standby , An ending acoustic icon that is played when the interaction flow between the user and the application ends, becomes inactive, or enters standby mode. The start sound icon should itself reflect the nature of the application, but the end sound icon may be a reverse playback of the sound of the start icon. The application may use useful acoustic icons. The audio contains hints about the nature of the application or the actual feedback type associated with this acoustic icon. For example, an application that provides a weather forecast reproduces an acoustic icon having sound related to the weather such as wind in the case of stormy weather, rain sound in the case of rainy weather, and a crying sound in case of fine weather. Another example of an acoustic icon is one that is used to provide status and information updates during times when the application is active. For example, a personal digital assistant application has several acoustic icons that provide the user with different types of status feedback regarding appointments, incoming emails, report deadlines, etc. For example, the personal digital assistant may repeatedly remind the user about the appointment using a suitable acoustic icon so that the reminder becomes increasingly persistent as the appointment approaches.

  In a preferred embodiment of the present invention, the user can enter and specify suitable information in the user profile which application he wishes to listen to in the dialog flow. It is also possible to specify the size of the acoustic icon and the number of times the acoustic icon is played during the dialogue flow. It is also possible to prioritize various applications so that feedback from intercom takes precedence over applications such as personal digital assistants. In this way, the user can be notified of the application with the higher priority when the application with the higher priority and the application with the lower priority notify the feedback at the same time in the dialog flow. The user profile is examined periodically or whenever it is modified by the acoustic icon manager to determine whether the acoustic icon should be played, the desired size, and the number of times this acoustic icon should be played during this interaction flow.

  In a further preferred embodiment, the dialog management system can determine user preferences by interpreting the dialog flow. For example, if the application notifies an appointment reminder that is closer to the appropriate acoustic icon and the user responds “Yes, I know”, the dialog management system does not need to be reminded any more by the user. This means that the sound icon for the next feedback by the application is suppressed. This level of “intelligent” interpretation on the side of the dialog management system may be indicated by the user in the user profile. A dialogue management system used by one or more users preferably sets up multiple user profiles, each user having his own private user profile and can specify his own personal preferences. .

  The dialogue management system according to the present invention can execute a part of the above processing steps by incorporating a software module or a computer program product. Such a computer program product can be loaded directly into the memory of a programmable dialog management system. Some of the units and modules such as the core dialog engine, application interface unit, and acoustic icon management unit can be realized in the form of computer program modules. The necessary software and algorithms may be encoded for the hardware device processor. Also, existing electronic devices can be easily adapted to benefit from the features of the present invention. Alternatively, the units or blocks that process user input and output prompts as described above can equally be implemented using hardware modules.

  Other objects and features of the present invention will become apparent from the following detailed description when read in conjunction with the accompanying drawings. However, it should be understood that the drawings are drawn for purposes of illustration only and are not intended to limit the invention. See the appended claims for limitations.

  Although the figures are described, other possible implementations of the invention are not excluded and the system is shown as part of a user device (eg, a home interaction system). For clarity of explanation, the interface between the user and the device according to one embodiment of the present invention is not shown.

  FIG. 1 shows a plurality of external applications A1, A2, A3,. . . 1 shows a dialog management system 1 having an interface for communicating with An. Applications A1, A2, A3,. . . , An is shown in a simplified form as a block, but in practice it can be any kind of “application” or “function” and the user wants to be notified about it or wants to control it in some way. . In this embodiment, the applications A1, A2, A3,. . . An includes, inter alia, a personal digital assistant A1, a news and weather forecast service A2, and a telephone A3.

  The dialogue management system 1 includes the dialogue management system 1 and the applications A1, A2, A3,. . . , An includes an application interface 10 for processing input / output information sent to and from An. Further, the dialogue management system 1 includes each application A1, A2, A3,. . . , An can be obtained from the application information regarding the sound icon provided by An and when the sound icon should be reproduced. This information is stored in the acoustic icon management unit 11. In this embodiment, one of the applications A1 automatically provides the dialog management system 1 with all relevant information regarding the set of acoustic icons. The related information is information such as when the application A1 is started, that is, booted. The other application A3 may send only descriptive information about the acoustic icon in advance and send a single acoustic icon on demand if the acoustic icon is actually needed in the dialogue flow. . The dialogue management system 1 includes applications A1, A2, A3,. . . , An when the applications A1, A2, A3,. . . , An can be requested to provide information on one or more acoustic icons as needed.

  Not all applications have a complete set of suitable acoustic icons that are free. Some applications do not have an acoustic icon or have the same acoustic icon. In order to cope with such a situation, the acoustic icon management unit 11 can select a suitable one from the predetermined collection 13 of acoustic icons and assign the acoustic icon to the application A2. In the case of such an application, the user may prefer that the acoustic icon management unit 11 assign a specific sound recording to the application A2. For example, when the weather forecast service A2 reports sunny weather, you may want to hear birds cry. In the case of a storm forecast, you may want to hear the sound of thunder. The user can input these recordings as audio data in a suitable format via the user interface, and have the acoustic icon management unit 11 assign the weather forecast service application A2. As another method of providing the acoustic icon management unit 11 having such a recording, there is a method of downloading from an external computer or a network 12 such as the Internet via a suitable interface 14.

  With different methods of acquiring the acoustic icon information, the dialogue management system 1 can collect all the necessary information to reproduce the necessary acoustic icons as needed in the dialogue flow.

  The dialogue flow in this embodiment includes various applications A1, A2, A3,... Operated by a dialogue management system 1 with a user (not shown). . . , An is configured by communication with An. The user issues spoken commands. That is, the dialogue management system 1 is requested through the microphone 5. The utterance command or request is recorded and digitized by the input detection mechanism 4. The input mechanism 4 sends the recorded voice input to the core dialog engine 8. The engine 8 has a block for executing normal steps included in speech recognition. The audio interface block 20 performs digital signal processing necessary for the input voice signal before sending it to the automatic voice recognizer 221. By this processing, a recognizable speech component is extracted from the input audio signal and sent to the language understanding block 22. In language understanding block 22, the relevance of the user's utterance command or request is analyzed and appropriately sent to dialog controller 23. The dialog controller 23 receives user input from the appropriate applications A1, A2, A3,. . . , An command that can be executed by An.

  When further information needs to be obtained from the user, for example, when the automatic speech recognition block 21 and the language understanding block 22 cannot interpret or understand the utterance command, or the applications A1, A2, A3,. . . , An, the dialog controller 23 generates an appropriate request and sends it to the audio generator 24. The request is synthesized by the voice generator 24. The audio interface block 20 performs digital signal processing necessary for the output audio signal. The output audio signal is then converted into an audible audio 7 by an audio output mechanism 6 such as a loudspeaker.

  In the exemplary embodiment of the dialog flow controlled by the dialog management system shown in FIG. 1, the user may wish to enter a schedule in his personal digital assistant A1 diary. The user only has to say “Enter appointment with tax advisor at 11:00 am next Monday”. The core dialog engine 8 converts the command into an appropriate format and sends it to the personal digital assistant A1. When the appointment can be input to the personal digital assistant A1 without any problem, an appropriate feedback is notified to the dialog management system 1. The dialogue management system 1 selects an appropriate confirmation feedback to be output (for example, an utterance such as “OK” or “OK”).

  If a schedule has already been entered at the same time of the day, the personal digital assistant A1 notifies the dialog management system 1. In the dialog management system 1, the application interface 10 and / or the dialog controller 23 interprets a response from the application and selects an appropriate acoustic icon. For example, a cymbal sound indicates that a new appointment collides with an already entered appointment. The interaction controller 23 also triggers the generation of a suitable prompt. For example, “No one has an appointment with 11:00”. Optionally, the user may deactivate the prompt output if detailed feedback is not required.

  In this embodiment, the user specifies his / her preference for playing audio icons in the user profile, and customizes or sets the range in which he / she wants to be notified of events that occur in the application he / she uses and which application has priority in the interaction flow. ing. These preferences may be retained until the user later changes them or may be temporary. For example, the user can tell the dialog management system how to react within a certain amount of time. For example, if the user orders "Do not disturb for 2 hours unless really important", the dialog management system will notify you of unimportant events (such as automatic weather forecast updates) that occurred within that 2 hours Refrain from. And all relatively unimportant events (for example, upcoming 24 hour reminders, such as “Dentist at 3pm tomorrow”) are delayed by 2 hours. Users are interrupted only for relatively important events. Relatively important events are, for example, appointments scheduled within that time, such as “15 minutes after meeting with the director” or a call from a customer tagged as important to the telephone application A3. It is. The dialogue management system examines the information specified in the user profile 3 to determine what is important and what is relatively unimportant.

  Another preference may be to specify the priority that is given to an application when two or more applications play an audio icon simultaneously. In this case, the designation of the user profile 13 by the user has a higher priority for the telephone A3 than for the news and weather forecast service A2. If a call is received at the same time that the news and weather forecast service A2 is automatically giving the latest news, the application interface 10 knows that the telephone application A3 has a higher priority, and the news and weather The acoustic icon of the forecast service A2 is suppressed. The sound icon of the news and weather forecast service A2 may be delayed and output later.

  Although the invention has been disclosed in the form of preferred embodiments and variations thereof, it will be appreciated that many further modifications and variations can be envisaged without departing from the scope of the invention. For example, the acoustic icon manager may be implemented as part of the core dialog engine or may be incorporated in another module such as a dialog controller. In one embodiment of the present invention, the dialogue system can process a word or two to determine the current voice quality of the user, and the user can inform the system by entering an identification code. . This identification code can be used to access stored user profile information or to generate appropriate control parameters for the audio interface.

  For the sake of clarity, in this application, “one” does not exclude a plurality of cases, and “having” does not exclude other steps or elements. “Non-part” and “module” do not limit the implementation in a single unit or module.

It is a block diagram which shows the dialogue management system by one Embodiment of this invention.

Claims (13)

A method of driving multiple applications by a common dialog management system,
Assign a unique set of acoustic icons to each application,
The common dialog management system notifies the user of the state of the application by playing back a related acoustic icon selected from a set of unique acoustic icons for each application at a point in time of the dialog flow. Method. The method of claim 1, comprising:
A method of playing back an acoustic icon of an application to indicate to the user a change in the operating state of the application. The method according to claim 1 or 2, wherein
A method wherein an application sends a set of audible icons and associated instructions regarding their use to the dialog management system. The method of claim 3, comprising:
An identification information of an individual audible icon of an application and associated instructions is obtained by the dialogue management system, and the audible icon is read from the application by the dialogue management system on demand. The method of claim 3, comprising:
A method wherein a complete set of acoustic icons for an application is obtained by the interaction management system at the beginning of an interaction flow between the user and the application, or upon launching or incorporation of the application. A method according to any one of claims 1 to 5, comprising
The interaction management system may modify the unique acoustic icon in the set of acoustic icons for the application and / or select a unique acoustic icon for the application from a collection of acoustic icons. A method comprising providing a set of icons to an application. A method according to any one of claims 1 to 5, comprising
The set of acoustic icons to be played in the interaction flow between the user and the application includes at least one unique starting acoustic icon to be played at the beginning of the interaction flow and / or at least one unique end to be played at the end of the interaction flow. A method comprising: an acoustic icon. A method according to any one of claims 1 to 5, comprising
The set of acoustic icons to be played in the interaction flow between the user and the application is an acoustic icon having some unique information to be played at a certain point in the interaction flow, and each acoustic icon is a specific type from the application. A method characterized by having an acoustic icon describing the feedback. A method according to any one of claims 1 to 8, comprising
A method wherein the acoustic icon and / or the playback characteristics of the acoustic icon are specified for a user in a user profile. A dialogue management system for running several applications,
An input detection mechanism for detecting user input to the system;
An audio output mechanism for outputting audible prompts;
A core interaction engine that coordinates the interaction flow by interpreting user input and generating output prompts;
An application interface for communication between the dialog management system and the application;
A source of a set of unique acoustic icons assigned to the application;
And a sound icon management unit that selects a related sound icon from a set of unique sound icons corresponding to the application and reproduces the sound icon at each point in the dialogue flow. The dialogue management system according to claim 11,
A system comprising means for allowing the user to input an acoustic icon. The dialogue management system according to claim 11 or 12,
A system having an interface for obtaining a set of acoustic icons or individual acoustic icons from an external source.   11. A computer program that can be directly loaded into a memory of a programmable dialog management system, wherein the steps of the method according to any one of claims 1 to 10 are executed when the computer program is run on the dialog management system. A computer program comprising a software code portion.

Images